Image collating apparatus, image collating method, image collating program and computer readable recording medium recording image collating program

• US 7,512,275 B2
• Filed: 10/19/2004
• Issued: 03/31/2009
• Est. Priority Date: 10/21/2003
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Itoh, Yasufumi, Onozaki, Manabu, Yumoto, Manabu, Okamoto, Toshiya, Horiyama, Takashi
• Primary Examiner(s): Ahmed, Samir A.
• Assistant Examiner(s): Woldemariam, Aklilu K
• Application Number:
  US10/967,145
• Publication Number:
  US 20050084155A1
• Time in Patent Office: 1,624 Days
• Field of Search: 382/224
• US Class Current: 382/224
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

When first and second images are input, a partial image feature calculating unit calculates feature values of partial images of the two images. A maximum matching score position searching unit searches for a position of the second image that attains to the highest matching score with each of the partial images of the first image. A movement-vector-based similarity score calculating unit calculates similarity between the first and second images, using information related to that partial image whose movement vector has direction and length within a prescribed range, which movement vector representing positional relation between a reference position for measuring, for each of the partial images, the position of the partial image in the first image and the position of the maximum matching score corresponding to the partial image searched out by the maximum matching score position searching unit. The images as the object of collation may belong to the same category classified based on the feature values.

Claims

1. An image collating apparatus, comprising:

partial image feature value calculating means for calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is one of three different values and wherein said one of three different values respectively represent that said partial area image has a pattern extending along the vertical direction, a pattern extending along the horizontal direction and other pattern, and outputting the value as a partial image feature value;

maximum matching score position searching means for searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

similarity score calculating means for calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out by said maximum matching score position searching means; and

determining means for determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched by said maximum matching score position searching means is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

2. The image collating apparatus according to claim 1, further comprising

category determining means for determining, based on the partial image feature value output by said partial image feature value calculating means for one of two images, a category to which said one image belongs;

wherein

said the other image is selected based on the category of said one image determined by said category determining means.

3. The image collating apparatus according to claim 2, wherein said the other image belongs to the same category as said one image.

4. The image collating apparatus according to claim 2, wherein

when a plurality of images are prepared as said the other image, one image among said plurality of the other images that belong to the same category as said one image is selected with priority.

5. The image collating apparatus according to claim 1, wherein

said maximum matching score position searching means searches that partial area set in said the other image which has the same said partial image feature value as said partial image feature value of the partial area image set in said one image.

6. The image collating apparatus according to claim 1, wherein

when said partial image feature value of the partial area image set in said one image indicates that said pattern extends along one of said vertical direction and said horizontal direction, said maximum matching score position searching means searches that partial area of the image set in said the other image of which said partial image feature value indicates said pattern extending along said one direction and searches that partial area of the image set in said the other image of which said partial image feature value indicates said other pattern.

7. The image collating apparatus according to claim 1, wherein

said partial area having said partial image feature value indicating said other pattern is excluded from the search by said maximum matching score position searching means.

8. The image collating apparatus according to claim 1, wherein

said partial image feature value calculating means calculates maximum length of consecutive pixels along horizontal direction and maximum length of consecutive pixels along vertical direction, and outputs said partial image feature value based on values indicating respective maximum lengths.

9. The image collating apparatus according to claim 1, wherein

said partial image feature value calculating means extracts strings of pixels representative of horizontal and vertical directions, from each of said partial area images, and based on a number of changes in pixel value in each extracted string of pixels, outputs said partial image feature value.

10. The image collating apparatus according to claim 1, wherein

said partial image feature value calculating means provides, for each of said partial area images, an image by displacing the partial area image to the left and right by a prescribed number of pixels and superposing the resulting images, and an image by displacing the partial area image upward and downward by a prescribed number of pixels and superposing the resulting images;

calculates a difference in pixel value between the image obtained by displacing each partial area image to the left and right by a prescribed number of pixels and superposing and the corresponding partial area image, and a difference in pixel value between the image obtained by displacing the partial area image upward and downward by a prescribed number of pixels and superposing and the corresponding partial area image; and

outputs said partial image feature value based on the calculated differences.

11. An image collating method, comprising a processor to implement the steps of:

partial image feature value calculating step of calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is one of three different values and wherein said one of three different values respectively represent that said partial area image has a pattern extending along the vertical direction, a pattern extending along the horizontal direction and other pattern, and outputting the value as a partial image feature value;

maximum matching score position searching step of searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

similarity score calculating step of calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out in said maximum matching score position searching step; and

determining step of determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched in said maximum matching score position searching step is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

12. An image collating method comprising a processor to implement:

calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is one of three different values and wherein said one of three different values respectively represent that said partial area image has a pattern extending along the vertical direction, a pattern extending along the horizontal direction and other pattern, and outputting the value as a partial image feature value;

searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out; and

determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

13. A computer readable recording medium recording an image collating program causing a computer to execute an image collating method, said method including

partial image feature value calculating step of calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is one of three different values and wherein said one of three different values respectively represent that said partial area image has a pattern extending along the vertical direction, a pattern extending along the horizontal direction and other pattern, and outputting the value as a partial image feature value;

maximum matching score position searching step of searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

similarity score calculating step of calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out in said maximum matching score position searching step; and

determining step of determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched in said maximum matching score position searching step is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

14. An image collating apparatus, comprising:

partial image feature value calculating unit calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is one of three different values and wherein said one of three different values respectively represent that said partial area image has a pattern extending along the vertical direction, a pattern extending along the horizontal direction and other pattern, and outputting the value as a partial image feature value;

maximum matching score position searcher searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

similarity score calculating unit calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out by said maximum matching score position searcher; and

determining unit determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched by said maximum matching score position searching means is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

15. An image collating apparatus, comprising:

partial image feature value calculating unit calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is a plurality of different values and wherein two of said plurality of different values include a value indicating said partial area image has a pattern extending along the vertical direction and a value indicating partial area image has a pattern extending along the horizontal direction, and outputting the value as a partial image feature value;

maximum matching score position searcher searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

similarity score calculating unit calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out by said maximum matching score position searcher; and

determining unit determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched by said maximum matching score position searching means is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

16. The image collating apparatus according to claim 15, wherein the partial image feature value calculating unit compares the value indicating said partial area image has a pattern extending along the vertical direction and the value indicating partial area image has a pattern extending along the horizontal direction, and wherein

a result of the comparison being the value of the partial image feature value outputted by the partial image feature value calculating unit.

17. The image collating apparatus according to claim 15, wherein the partial image feature value calculating unit compares the value indicating said partial area image has a pattern extending along the vertical direction and the value indicating partial area image has a pattern extending along the horizontal direction, and wherein

if a result of the comparison provides a direction having a larger value being horizontal, outputting a value representing a horizontal direction being the value of the partial image feature value outputted by the partial image feature value calculating unit,

if a result of the comparison provides a direction having a larger value being vertical, outputting a value representing a vertical direction being the value of the partial image feature value outputted by the partial image feature value calculating unit, and

if a result of the comparison is neither of a direction having a larger value being vertical or a direction having a larger value being horizontal, outputting a predetermined value being the value of the partial image feature value outputted by the partial image feature value calculating unit.

18. An image collating method comprising a processor to implement:

calculating, on each of a plurality of partial area images set in an image, a value reflecting a pattern of the image of the partial area, wherein said partial image feature value is a plurality of different values and wherein two of said plurality of different values include a value indicating said partial area image has a pattern extending along the vertical direction and a value indicating partial area image has a pattern extending along the horizontal direction, and outputting the value as a partial image feature value;

searching, for each of a plurality of partial area images set in one of two images, for a maximum matching score position of the other of the two images, which is a position of a partial area image having the maximum matching score with the partial area image;

calculating a similarity score between the two images and outputting an image similarity score, using information related to that partial area of which positional relation amount is within a prescribed range, said positional relation amount representing positional relation between a reference position, for each of said partial areas, for measuring a position of the partial area within said one image, and said maximum matching score position corresponding to the partial area searched out; and

determining whether said two images match or not, based on said image similarity score applied thereto;

wherein

scope of said the other image searched by said maximum matching score position searching means is selected and determined from among a plurality of partial areas set in said the other image in accordance with said partial image feature value of the partial area image set in said one image.

19. The image collating method according to claim 18, wherein the partial image feature value calculating unit compares the value indicating said partial area image has a pattern extending along the vertical direction and the value indicating partial area image has a pattern extending along the horizontal direction, and wherein

a result of the comparison being the value of the partial image feature value outputted by the partial image feature value calculating unit.

20. The image collating method according to claim 18, wherein the partial image feature value calculating unit compares the value indicating said partial area image has a pattern extending along the vertical direction and the value indicating partial area image has a pattern extending along the horizontal direction, and wherein

if a result of the comparison provides a direction having a larger value being horizontal, outputting a value representing a horizontal direction being the value of the partial image feature value outputted,

if a result of the comparison provides a direction having a larger value being vertical, outputting a value representing a vertical direction being the value of the partial image feature value outputted, and

if a result of the comparison is neither of a direction having a larger value being vertical or a direction having a larger value being horizontal, outputting a predetermined value being the value of the partial image feature value outputted.